Prion diseases are a set of neurodegenerative conditions caused by prion protein (PrP). Neurodegenerative conditions are caused by misfolded variations of the normal PrP found in the brain, denoted as PrPC. Once a misfolded variant, denoted as PrPSC, is introduced to a healthy brain environment, the healthy variants are also misfolded which inhibits cells from functioning properly. The PrPSC proteins aggregate in the brain in plaque formations, inhibiting vital processes and leading to decreased mobility, memory impairment, and eventually death. Recently, ribosomal profiling has been utilized to create cell profiles of prion disease progression leading to questions regarding the degeneration of certain subgroups of glial cells. Presently, the cell densities in the brain must be determined manually. Although they seem theoretically viable, neural networks are limited by their ability to quantify cells without massive training sets. The varying overlap of cells across regions of the brain makes it difficult and time-consuming for the neural network to differentiate cell bodies. Random forest classifiers use a set of predetermined values from gross image analysis to create an estimation of where various cell bodies are located. The forest classifier program, like a neural network, can be manually trained to improve its prediction of where cell bodies are located. The random forest classifier program is trained on healthy sets of mice brains, but will then be utilized on the scans from prion affected mice. The forest classifier program is trained such that it can quantify a variety of cell types. The study’s aim is to train the forest classifier program and analyze its prediction efficacy through visual analysis to determine if it is an effective tool for quantifying various glial subgroups in prion affected mice.